English
Related papers

Related papers: A Strong Composition Theorem for Junta Complexity …

200 papers

A composite likelihood is a combination of low-dimensional likelihood objects useful in applications where the data have complex structure. Although composite likelihood construction is a crucial aspect influencing both computing and…

Methodology · Statistics 2022-04-26 Zhendong Huang , Davide Ferrari

We study the problem of learning Gaussian Mixture Models (GMMs) and ask: which structural properties govern their sample complexity? Prior work has largely tied this complexity to the minimum pairwise separation between components, but we…

Machine Learning · Computer Science 2025-08-06 Farzad Aryan

A combinatorial principle CECA is formulated and its equivalence with GCH+ certain weakenings of Box_lambda for singular lambda is proved. CECA is used to show that certain ``almost point- < tau'' families can be refined to point- < tau…

We study the problem of testing whether an unknown $n$-variable Boolean function is a $k$-junta in the distribution-free property testing model, where the distance between functions is measured with respect to an arbitrary and unknown…

Computational Complexity · Computer Science 2018-02-15 Xi Chen , Zhengyang Liu , Rocco A. Servedio , Ying Sheng , Jinyu Xie

Sensitivity, block sensitivity and certificate complexity are basic complexity measures of Boolean functions. The famous sensitivity conjecture claims that sensitivity is polynomially related to block sensitivity. However, it has been…

Computational Complexity · Computer Science 2015-06-09 Andris Ambainis , Krišjānis Prūsis , Jevgēnijs Vihrovs

Given a function dictionary $\cal D$ and an approximation budget $N\in\mathbb{N}^+$, nonlinear approximation seeks the linear combination of the best $N$ terms $\{T_n\}_{1\le n\le N}\subseteq{\cal D}$ to approximate a given function $f$…

Machine Learning · Computer Science 2020-11-06 Zuowei Shen , Haizhao Yang , Shijun Zhang

In recent years, the usage of ensemble learning in applications has grown significantly due to increasing computational power allowing the training of large ensembles in reasonable time frames. Many applications, e.g., malware detection,…

Machine Learning · Computer Science 2021-11-18 Peter Domanski , Dirk Pflüger , Jochen Rivoir , Raphaël Latty

The well-known Kruskal-Katona theorem in combinatorics says that (under mild conditions) every monotone Boolean function $f: \{0,1\}^n \to \{0,1\}$ has a nontrivial "density increment." This means that the fraction of inputs of Hamming…

Computational Complexity · Computer Science 2019-11-04 Anindya De , Rocco A. Servedio

The assembly index of assembly theory quantifies the minimal number of composition steps required to construct an object from elementary components. The study proves that the decision version of the assembly index problem is NP-complete,…

Computational Complexity · Computer Science 2026-04-21 Piotr Masierak

A foundational theory of compositional categorical rewriting theory is presented, based on a collection of fibration-like properties that collectively induce and intrinsically structure the large collection of lemmata used in the proofs of…

Logic in Computer Science · Computer Science 2023-07-17 Nicolas Behr , Russ Harmer , Jean Krivine

In this work, a convergence lemma for function $f$ being finite compositions of analytic mappings and the maximum operator is proved. The lemma shows that the set of $\delta$-stationary points near an isolated local minimum point $x^*$ is…

Computer Science and Game Theory · Computer Science 2022-08-12 Xiaotie Deng , Hanyu Li , Ningyuan Li

Rademacher complexity is often used to characterize the learnability of a hypothesis class and is known to be related to the class size. We leverage this observation and introduce a new technique for estimating the size of an arbitrary…

Machine Learning · Computer Science 2018-01-30 Jonathan Kuck , Ashish Sabharwal , Stefano Ermon

We show that the deterministic decision tree complexity of a (partial) function or relation $f$ lifts to the deterministic parity decision tree (PDT) size complexity of the composed function/relation $f \circ g$ as long as the gadget $g$…

Computational Complexity · Computer Science 2023-10-19 Arkadev Chattopadhyay , Nikhil S. Mande , Swagato Sanyal , Suhail Sherif

This paper is concerned with the study of the consistency of a variational method for probability measure quantization, deterministically realized by means of a minimizing principle, balancing power repulsion and attraction potentials. The…

Functional Analysis · Mathematics 2013-10-07 Massimo Fornasier , Jan-Christian Hütter

We consider the problem of sampling from a density of the form $p(x) \propto \exp(-f(x)- g(x))$, where $f: \mathbb{R}^d \rightarrow \mathbb{R}$ is a smooth and strongly convex function and $g: \mathbb{R}^d \rightarrow \mathbb{R}$ is a…

Machine Learning · Statistics 2019-10-02 Wenlong Mou , Nicolas Flammarion , Martin J. Wainwright , Peter L. Bartlett

We consider the problem of detecting a small subset of defective items from a large set via non-adaptive "random pooling" group tests. We consider both the case when the measurements are noiseless, and the case when the measurements are…

Information Theory · Computer Science 2011-07-25 Chun Lam Chan , Pak Hou Che , Sidharth Jaggi , Venkatesh Saligrama

Over a finite field $\F_q$ the $(n,d,q)$-Reed-Muller code is the code given by evaluations of $n$-variate polynomials of total degree at most $d$ on all points (of $\F_q^n$). The task of testing if a function $f:\F_q^n \to \F_q$ is close to…

Information Theory · Computer Science 2015-03-20 Noga Ron-Zewi , Madhu Sudan

Leveraging tools of De, Mossel, and Neeman [FOCS, 2019], we show two different results pertaining to the \emph{tolerant testing} of juntas. Given black-box access to a Boolean function $f:\{\pm1\}^{n} \to \{\pm1\}$, we give a $poly(k,…

Data Structures and Algorithms · Computer Science 2021-06-02 Vishnu Iyer , Avishay Tal , Michael Whitmeyer

ProBoost, a new boosting algorithm for probabilistic classifiers, is proposed in this work. This algorithm uses the epistemic uncertainty of each training sample to determine the most challenging/uncertain ones; the relevance of these…

We study the problem of testing if a function depends on a small number of linear directions of its input data. We call a function $f$ a linear $k$-junta if it is completely determined by some $k$-dimensional subspace of the input space. In…

Computational Complexity · Computer Science 2018-11-05 Anindya De , Elchanan Mossel , Joe Neeman
‹ Prev 1 3 4 5 6 7 10 Next ›